US20210256848A1 - Moving body tracking system, moving body tracking method, and program - Google Patents

Abstract

A moving body tracking system, comprising: a first camera that captures image(s) of moving body entering an intersection, a plurality of second cameras installed in a plurality of locations set as destinations of the moving body entering the intersection, a moving direction determining part that determines a moving direction of the moving body entering the intersection due to a change in direction of the moving body based on captured data by the first camera, and a path specifying part that selects the second camera based on the moving direction of the moving body, searches a frame in which the specified moving body was captured from captured data by the second camera, and specifies a path of the moving body.

Description

• This application is a National Stage Entry of PCT/JP2019/034824 filed on Sep. 4, 2019, which claims priority from Japanese Patent Application 2018-165566 filed on Sep. 5, 2018, the contents of all of which are incorporated herein by reference, in their entirety.
FIELDDescription of Related Applications
• This application is based upon and claims the benefit of the priority of Japanese patent application No. 2018-165566 filed on Sep. 5, 2018, the disclosure of which is incorporated herein in its entirely by reference thereto.
• The present invention relates to a moving body tracking system, a moving body tracking method, and a program.
BACKGROUND
• Origin-Destination (OD) surveys have been conducted as basic data for formulating road improvement plan and urban development plan. For example, the Ministry of Land, Infrastructure, Transport and Tourism (MLIT) conducts a nationwide OD survey every five years.
• Patent Literature 1 discloses an automatic traffic volume measurement apparatus and an automatic traffic volume measurement system that can automatically measure moving object and consolidate the measurement results. According to the literature, this automatic traffic volume measurement apparatus comprises a moving object detection means, which compares a still image of a frame of video captured by a video camera with a reference image that serves as a comparison basis, and detects the presence of the moving object in the still image according to the comparison results. This automatic traffic volume measuring apparatus further comprises a type identifying means, which identifies the type of the moving object based on the pixels area of the image detected as the moving object by the moving object detecting means. This automatic traffic volume measurement apparatus further comprises a speed calculating means, which calculates the moving speed of the moving object based on the number of consecutive pluralities of the still images in which the presence of the moving object has been detected by the moving object detecting means. This automatic traffic measurement apparatus further comprises a data generating means to generate descriptive data that describes the images captured by the video camera in association with at least the type of the moving object, its moving speed, and the time at which it was detected.
• Patent Literature 2 discloses a traffic information management apparatus that is capable of accurately and efficiently tracking a particular vehicle traveling on a road. According to this document, the traffic information management apparatus comprises traffic information collection apparatuses200atof, which are formed of cameras and other apparatuses installed at multiple points P1 to P6 on the road. By way of respective traffic information collection devices detecting the size, color, and other features of vehicles, the travel time(s) T1 to T5 between respective apparatuses is estimated. Based on the estimated travel time(s), the arrival time(s) of the particular vehicle at respective points are predicted, and the particular vehicle is detected at the predicted time(s). This improves the detection accuracy of the specific vehicle.
• Patent Literature 3 discloses a traffic flow measurement apparatus that is capable of not decreasing recognition accuracy even if some or all of the vehicles are not detected. According to the same document, this traffic flow measurement apparatus comprises a location correction means24 that extracts vehicle candidates from the image data at time t and corrects the position of the vehicle candidates whose mapping to time (t−1) has been completed using a predicted position. This traffic flow measurement apparatus also comprises a vehicle candidate correction means25 that adds vehicle(s) that failed to be extracted to the vehicle candidates by giving their predicted position(s). This traffic flow measurement apparatus also comprises a passing judgment means26 that determines vehicle candidate(s) that does not exist in a predetermined area as passing vehicle(s), and calculates traffic information by taking into account the location correction or addition of vehicle candidate(s) and passing vehicle(s).
• [Patent Literature 1] Japanese Patent Kokai Publication No. JP2005-4426A
• [Patent Literature 2] Japanese Patent Kokai Publication No. JP2000-353290A
• [Patent Literature 3] Japanese Patent Kokai Publication No. JPH08-147591A
SUMMARY
• The following analysis is given by the present invention. The OD survey as mentioned above has problems of being costly and time-consuming because it also uses questionnaires in combination. On the other hand, various devices have been proposed to identify moving bodies, such as people and vehicles, from images captured by cameras and other devices, and the accuracy of these devices has been improved (see Patent Literatures 1-3). However, the automatic traffic measurement device ofPatent Literature 1 has the problem that it can only obtain descriptive data (description data) at the location where the video camera is installed. This is also the case with Patent Literature 3, which aims at measuring traffic flow using a camera that takes pictures of the road in the moving direction of a vehicle on the road.
• The configuration of Patent Literature 2 does not bear in mind tracking of vehicles turning right or left, and to do so would require the installation of a large number of cameras along the presumed moving direction of the vehicles, which would be costly.
• It is an object of the present invention to provide a moving body tracking system, a moving body tracking method and a program, which enable to contribute to reducing the cost and survey time required for tracking moving bodies such as vehicles entering an intersection.
• According to a first aspect of the invention, there is provided a moving body tracking system, comprising: a first camera that captures image(s) of moving body entering an intersection, a plurality of second cameras installed in a plurality of locations set as destinations of the moving body entering the intersection, a moving direction determining part that determines a moving direction of the moving body entering the intersection due to a change in direction of the moving body based on captured data by the first camera, and a path specifying part that selects the second camera based on the moving direction of the moving body, searches a frame in which the specified moving body was captured from captured data by the second camera, and specifies a path of the moving body.
• According to a second aspect of the invention, there is provided a moving body tracking method, comprising: determining a moving direction of a moving body entering an intersection based on a captured data by a first camera capturing the moving body entering the intersection, and selecting a second camera from a plurality of cameras installed in a plurality of locations determined as destinations of the moving body entering the intersection based on the moving direction of the moving body, and specifying a moving path of the moving body by searching frame(s) in which the moving body is captured from the captured data of the second cameras.
• According to a third aspect of the invention, there is provided a program for causing a computer that is capable of accessing captured data captured respectively, by a first camera that captures an image(s) of a moving body entering an intersection, and a plurality of second cameras installed in a plurality of locations determined as destinations of the moving body entering the intersection, to perform: a process that determines a path direction of the moving body entering the intersection based on the captured data by the first camera, and a process that selects the second camera based on a path direction of the moving body, and specifies a path of the moving body by searching a frame(s) in which the moving body is captured from the captured data of the second camera. It is to be noted that this program can be recorded on a computer-readable (non-transient) storage medium. That is, the present invention can be implemented as a computer program product.
• According to the present invention, it is possible to provide a moving body tracking system, a moving body tracking method, and a program, which contribute to reducing the cost and time required to track and investigate moving bodies such as vehicles entering an intersection. That is, the present invention transforms the configuration for tracking and surveying moving bodies described in the background technology into a configuration that is significantly improved in terms of its cost and survey time.
BRIEF DESCRIPTION OF THE DRAWINGS
• FIG. 1 is a diagram showing a configuration of an example embodiment of the present invention.
• FIG. 2 is a diagram showing a description of an operation of an example embodiment of the present invention.
• FIG. 3 is a diagram showing a description of an operation of an example embodiment of the present invention.
• FIG. 4 is a diagram showing a configuration of a moving body tracking system according to a first example embodiment of the present invention.
• FIG. 5 is a diagram showing an example of information stored in tagged and captured data storage part of a moving body tracking system according to a first example embodiment of the present invention.
• FIG. 6 is a diagram illustrating a function of an image tagging engine.
• FIG. 7 is a diagram showing an example of information stored in moving body path tracking data storage part of an example embodiment of the present invention.
• FIG. 8 is a flowchart showing an operation of moving body tracking system of an example embodiment of the present invention.
• FIG. 9 is a diagram showing a description the tracking operation of the moving body by the moving body tracking system of a first example embodiment of the present invention.
• FIG. 10 is a diagram showing a configuration of a moving body tracking system according to a second example embodiment of the present invention.
• FIG. 11 is a diagram showing an example of a path display by the second example embodiment of the present invention.
• FIG. 12 is a diagram showing a configuration of a computer formulating a moving body tracking system according to the present invention.
PREFERRED MODES
• First, an outline of one mode of this invention will be described with reference to the drawings. Reference numbers referring to the drawings mentioned in this outline are for convenience as an example for facilitating understanding, and not intended to limit the present invention to the illustrated modes. And respective connection line(s) between blocks in the reference drawing appearing in the following description includes both bi-directional and single-directional. A single-directional arrow describes a main data flow schematically, which, however, does not exclude bidirectionality. In the following description, “A and/or B” is used in the sense of A and B, or A or B. The program is executed via a computer apparatus, and the computer apparatus is equipped with, for example, a processor, a storage device, an input device, a communication interface, and a display device if necessary. The computer apparatus is also configured to be able to communicate with devices (including computers) inside or outside the device via the communication interface, irrespective of wired or wireless. In the following description, “A and/or B” is used in the sense of at least one of A and B.
• In one example embodiment thereof, the present invention can be realized by a movingbody tracking system20A that includes afirst camera11, a plurality ofsecond cameras12A,12B, a movingdirection determining part21, and apath specifying part22, as shown inFIG. 1. More concretely, thefirst camera11 captures an image(s) of a moving body entering an intersection (e.g., intersection A inFIG. 1). Thesecond cameras12A and12B are installed in a plurality of locations as destinations for the moving body entering the intersection and capture an image(s) of the moving body passing through the intersection.
• Based on the captured data of thefirst camera11, the movingdirection determining part21 determines the moving direction of the moving body due to a change in direction of the moving vehicle entering the intersection. For example, as shown inFIG. 2, when a vehicle V enters an intersection A and turns right, the movingdirection detecting part21 determines that the vehicle V has turned right based on the captured data of thefirst camera11.
• Then, thepath specifying part22 selects thesecond camera12A based on the moving direction of the moving body, and identifies the moving path of the moving body by searching (in) the frame in which the identified moving body has been captured from the captured data of thesecond camera12A. For example, as shown inFIG. 3, when thepath specifying part22 confirms the movement of a vehicle whose identification information (CAR) is42 from the captured data of thesecond camera12A, it determines that the vehicle has moved from the intersection A to a Location B1 where thesecond camera12A is installed. By repeating the same kind of processing, it is possible to track a moving body that moves through multiple sections.
• In this way, the movingbody tracking system20A identifies the path of a moving body such as a vehicle that has entered an intersection. As is clear from the above description, the movingdirection determining part21 determines the moving direction of the moving body, and thepath specifying part22 selects the second camera based on this moving direction. This makes it possible to reduce the number of cameras installed and to track the moving body efficiently, thereby reducing costs and investigation time.
First Example Embodiment
• Then, a first example embodiment of the present invention applied to OD survey will be described in detail with reference to the drawings.FIG. 4 shows a configuration of a moving body tracking system according to the first example embodiment of the present invention. Referring toFIG. 4, a configuration is shown including a plurality ofcameras10, animage tagging engine40, a tagged captureddata storage part50, a moving body tracking system20, and a moving body path data storage part60.
• A plurality ofcameras10 are placed, one at respective intersection of the area to be surveyed for OD.Respective camera10 is located at a position that can capture images of a moving body entering the intersection from the front, rear, left and right directions, and identify the moving direction of the moving body entering the intersection from respective directions. For intersections equipped with traffic lights, the power supplied to the traffic lights can be used as a power source for thesecameras10. Appropriate locations for installation of thecameras10 are selected depending on the intersection conditions and the focal length of the lens to be mounted. In this example embodiment, thesecameras10 will function as the first and second cameras described above.
• It is preferable that thecameras10 are of a portable type. By doing so, it is possible to bring thecameras10 to the area where the OD survey is to be conducted, install thecameras10 at the necessary locations, and conduct the survey, thereby allowing further reduction of the cost of the survey.
• Animage tagging engine40 is connected torespective cameras10 via thenetwork30, and analyzes the captured data taken by respective camera(s)10 to recognize and tag the object(s) in the captured data. An in-vehicle recognition device can be used as such animage tagging engine40. The captured data tagged by theimage tagging engine40 is stored in the tagged captureddata storage part50.
• A tagged captureddata storage part50 stores the tag information created by theimage tagging engine40 along with the captured data.
• FIG. 5 shows an example of information held in the tagged captureddata storage part50. The example inFIG. 5 shows tag information with the following parameters: object ID, frame number, box coordinate1, box coordinate2, object type, captured time, and camera location information.
• An example of the operation of theimage tagging engine40 will now be explained.FIG. 6 shows an example of the captured data input to theimage tagging engine40.
• Step P1: Theimage tagging engine40 extracts object(s) such as vehicle(s), bicycle(s), person(s), etc., from the captured data and adds a rectangular frame (also called as bounding box). Theimage tagging engine40 extracts object(s) such as vehicle(s), bicycle(s), person(s), etc., and assigns an ID (object ID) to respective detected object(s). Theimage tagging engine40 obtains the captured date and time, frame number, and location information of the camera (camera location information) of the captured data. These can be obtained from the metadata annexed to the captured data.
• Step P2: Theimage tagging engine40 acquires coordinates of the upper left corner (x1, y1) and lower right corner (x2, y2) of the rectangular frame (bounding box) when the upper left corner of the image is set as the origin (0, 0) for the rectangular frame. These coordinates correspond to the box coordinates 1 and 2 inFIG. 5. Box coordinates 1 and 2 make it possible to grasp (determine) the size of the object and its distance from the camera.
• Step P03: Theimage tagging engine40 determines whether the object extracted above is a vehicle, a bicycle or a person. The result of this determination becomes the object type information shown inFIG. 5. The object type can be determined using various methods, for example, by calculating the degree of similarity with predetermined standard object image(s), or by using AI (Artificial Intelligence). In this determination process, in case where the accuracy of the object type is obtained, it may be included in the tag information of the accuracy.
• In this way, respective information shown inFIG. 5 can be obtained. The above operations of theimage tagging engine40 and the tag information inFIG. 5 are only examples, and various changes can be made. For example, if license plate (“number plate”) information of a vehicle is obtained, it is possible to use the license plate number as an object ID of the vehicle.
• The moving body tracking system20 identifies the path of the moving body using the captured data and tag information stored in the above-tagged captureddata storage part50, and stores it in the moving body path data storage part60.
• More concretely, the moving body tracking system20 has a trackingtarget selecting part23, a movingdirection determining part21, aspeed estimation part24, and apath specifying part22.
• When the object ID to be tracked is input, the trackingtarget selecting part23 reads the data with the corresponding object ID from the tagged captureddata storage part50 and sends it to the movingdirection detecting part21.
• The movingdirection detecting part21 selects the frame with the oldest captured time and the frame with the newest captured time of the tag information exemplified inFIG. 5, and determines the moving direction of the moving body according to a change(s) in box coordinates 1 and 2. For example, if both the X and Y coordinates change significantly, the movingdirection determining part21 determines that the moving body (vehicle) has made a right or left turn at the intersection. On the other hand, if only one of the X and Y coordinates is changing significantly, the movingdirection detecting part21 determines that the moving body (vehicle) is running straight through the intersection. The movingdirection detecting part21 sends the object ID and the result of the determination to thespeed estimating part24.
• Thespeed estimating part24 selects a frame with an oldest captured time and a frame with a newest captured time of the tag information exemplified inFIG. 5, and calculates a moving distance of the moving body by changing the box coordinates' and2. Next, thespeed estimating part24 calculates the speed of the moving body by dividing the calculated distance traveled by the difference in the captured times. Thespeed estimating part24 sends the object ID and its estimated speed as a result of the determination to thepath specifying part22.
• Thepath specifying part22 calculates an intersection that the moving body is assumed to pass through next and its estimated arrival time based on the moving direction and estimated speed obtained by the movingdirection detecting part21 andspeed estimating part24, and the connection relationship between intersections. Then, thepath specifying part22 reads out the captured data of the estimated arrival time from the captured data taken by thecamera10 that is captured the corresponding intersection. If any object similar to an object identified by the object ID is captured in the read data, thepath specifying part22 determines that it is the same moving body and records it as the moving path of the corresponding object ID.
• Repeating the above operation, the moving body tracking system20 creates the path information of the moving body and stores it in the moving body path data storage part60.
• FIG. 7 shows an example of the path information held in the moving body path data storage part60. The example inFIG. 7 shows the path information of a moving body, which is configured by sequential recording of its passing location for respective object ID and its captured time.
• Next, the operation of this example embodiment will be described in detail with reference to the drawings.FIG. 8 is a flowchart representing the operation of the moving body tracking system according to the first example embodiment of the present invention. Referring toFIG. 8, first, the moving body tracking system20 selects a moving body to be tracked, starting from an arbitrary point (step S001). This selection of the moving body to be tracked may be instructed by the user, or it may be an object ID selected by the moving body tracking system20. For example, a scheme in which the moving body tracking system20 tracks all of the object IDs detected at any given location by referring to the tagged captureddata storage50 can also be adopted.
• Next, the moving body tracking system20 determines the moving direction of the moving body having the selected object ID (Step S002).
• Next, the moving body tracking system20 estimates a speed of the moving body having the selected object ID (Step S003).
• Next, the moving body tracking system20 identifies a path by referring to the data of the captured time obtained from the estimated speed in the captured data of the intersection to which the moving body having the selected object ID is moving (Step S004).
• And next, the moving body tracking system20 determines whether or not the tracking of the moving body having the selected object ID should be terminated (Step S005). The conditions for terminating the tracking of the moving body may be as follows. The first condition is when the moving body being tracked reaches an intersection at the end of the area in which the OD survey is conducted. In this case, the tracking can be terminated because the identification of the starting point, the ending point, and the path between them has been completed. The second condition is when loss of sight of the moving body under tracking has occurred. In this case, the reason may be that the moving body has stopped moving from the last intersection, for example, because it has reached its destination. In this case, too, the identification of the starting point, the end point, and the path between them has been completed, so the tracking can be terminated. Another reason for losing sight of the moving body under tracking is that the moving body made a U-turn in the middle of the road, and the tracking has failed. In this case, the survey may be terminated, or the search may be continued by expanding the search target.
• If, as a result of the above determination, it is determined that tracking is to be continued (NO in step S005), the moving body tracking system20 reads the captured data of the intersection which the corresponding moving body last entered and continues the processing of steps S002 to S004.
• On the other hand, if it is determined that the tracking is to be terminated (YES in step S005), the moving body tracking system20 records the path information exemplified inFIG. 7 in the moving body path data storage part60, and ends the processing.
• With reference toFIG. 9, the operation of the moving body tracking system20 of this example embodiment will be described in detail. In the following explanation, it will be assumed that an OD survey of a moving body originating from Location A is performed. For example, let us assume that a vehicle with object ID=42 passed Location A at 9:34:20 (hour:minute:second). In this case, the moving body tracking system20 estimates that the vehicle with object ID=42 is destined to Location B based on the captured data at Location A, and that an estimated time of arrival is 9:34:30.
• Next, based on the moving direction determined at Location A and the estimated time of arrival, the moving body tracking system20 identifies a vehicle that passed Location B at around 9:34:30 among the captured data at Location B. In the example inFIG. 9, the vehicle with object ID=42 and a vehicle ID with object ID=130 are shown (captured), but the moving body tracking system20 selects the vehicle with object ID=42, which has a more similar appearance. Then, the tracking system20 selects the vehicle with the object ID=42 based on the captured data at Location B.
• In the similar way, the moving body tracking system20 identifies the vehicle that passed Location C at around 9:34:40 among the captured data at Location C based on the moving direction determined at Location B and the estimated time of arrival. In the example inFIG. 9, the vehicle with object ID=42 and a vehicle with object ID=10 are shown, but the moving body tracking system20 selects the vehicle with object ID=42, which has a more similar appearance. In the same way below, the moving body tracking system20 confirms that the vehicle with object ID=42 has reached Location D, at which it ends the tracking.
• As explained above, according to this example embodiment, it is possible to track a moving body by installing one or more cameras per intersection. The reason for this is that the moving body tracking system20 has adopted a configuration to determine the moving direction and thereby track the moving body. This system also makes it possible to reduce the investigation time. The reason for this resides in that the moving body tracking system20 estimates the speed of the moving body and uses the estimated arrival time of the moving body to efficiently conduct tracking. Note, the moving bodies do not necessarily pass only the intersections at which the cameras are installed, and it is possible that a certain number of moving bodies may be lost from tracking, as described in step S005 above. However, the collection rate of questionnaires in the current OD survey is about 30 to 60% (conducted by the MLIT in fiscal year 2015), and the survey data can be sufficiently obtained with this method, too.
Second Example Embodiment
• Next, a second example embodiment, which uses the configuration of the first example embodiment above and adds a function of displaying map information representing a path of a particular moving body, will be described in detail with reference to the figures.FIG. 10 shows a configuration of the second example embodiment of the moving body tracking system. Referring toFIG. 10, a configuration in which a selection accepting and respondingpart25 is added to the movingbody tracking system20B is shown.
• The selection accepting and respondingpart25 comprises a function to display map information on a predetermined map that displays a movement path of a moving body accepted from a predetermined user terminal. Concretely, when the selection accepting and respondingpart25 receives a selection of a moving body from a predetermined user terminal, it takes out (retrieves) path information of the corresponding object ID from the moving body path data storage part60. Then, the selection accepting and respondingpart25 responds, to the user terminal, map information displaying a movement path of the moving body whose selection was accepted on a predetermined map.
• FIG. 11 shows an example of a path display mode of a moving body tracking system by the second example embodiment of the present invention. For example, it is assumed that the selection accepting and respondingpart25 accepts a designation of the vehicle with object ID=42 from a predetermined user terminal.
• In this case, the moving body tracking system retrieves the path information of an object with object ID=42 from the moving body path data storage60. The user terminal displays map information showing the moving path of the object with object ID=42 on a predetermined map, as shown inFIG. 11.
• The user of the user terminal can check a movement history of suspicious vehicle(s) by referring to such map information. Of course, it is also possible to specify a moving body other than a vehicle as an object ID and check (monitor) its movement history. For example, it is possible to track a bicycle(s) used by a criminal person to escape, which can be useful for criminal investigations.
• As described above, this invention can be used not only as an OD survey but also as a tracking system (displaying movement history) specifying any vehicle.
• Although the respective example embodiments of the present invention have been described above, the present invention is not limited to the above-described example embodiments, and further modifications, replacements, and adjustments can be made without departing from the basic technical concept of the present invention. For example, the network configuration, the configuration of respective elements, and the expression form of the message(s) shown in respective drawings are examples for helping understanding of the present invention, and are not limited to the configurations shown in these drawings.
• In addition, the procedure(s) shown in the above-described first to second example embodiments can be realized (implemented) as a program for causing a computer (9000 inFIG. 16) that functions as the moving body tracking system20/20A/20B to execute processing as the moving body tracking system. For example, this kind of computer has a configuration comprising Central Processing Unit (CPU)9010,Communication Interface9020,Memory9030, andAuxiliary Storage Device9040 as described inFIG. 12. That is, theCPU9010 ofFIG. 12 executes the moving direction determining program/speed estimating program, the data conversion program and refers to the calculating parameters held in theauxiliary storage device9040 to execute the processing.
• That is, every part (processing means, function) of moving body tracking system described in first and second example embodiments can be realized by a computer program that causes the processor in these systems to execute above processing using its hardwares respectively.
• Lastly, preferred modes of the present invention are outlined herein below.
[Mode 1]
• (Refer to above mentioned moving body tracking system of the first aspect of the present invention.)
[Mode 2]
• The moving body tracking system, further comprising a speed estimating part that estimates a speed of the moving body based on a location of the moving body recorded in the captured data by the first camera, wherein the path specifying part selects the captured data by the second camera based on the speed of the moving body.
[Mode 3]
• The moving body tracking system, wherein the cameras are installed in an intersection of an area in which an Origin-Destination (OD) survey is conducted, and the system comprises a function that performs the OD survey by causing the cameras to function as the first and/or second camera(s).
[Mode 4]
• The moving body tracking system, wherein the first camera is installed at a location that allows to capture the moving body entering the intersection, from the front, back, left and right directions, and identify the moving direction of the moving body entering the intersection, from respective direction.
[Mode 5]
• The moving body tracking system, further comprising: a path storage part that stores path information indicating a path for respective identified moving body, and a map information displaying part that displays map information displaying a path of the moving body accepted from a predetermined user terminal on a predetermined map.
[Mode 6]
• (Refer to above mentioned moving body tracking method of the second aspect of the present invention.)
[Mode 7]
• (Refer to above mentioned program of the third aspect of the present invention.)
• Mode 6 and Mode 7 can be expanded to Modes 2 to 5 likewise as theMode 1.
• It is to be noted that each of the disclosures in the abovementioned patent literatures is incorporated herein by reference. Modifications and adjustments of example embodiments and examples are possible within the bounds of the entire disclosure (including the claims) of the present invention, and also based on fundamental technological concept(s) thereof. Furthermore, a wide variety of combinations and selections (including partial deletions) of various disclosed elements is possible within the scope of the claims of the present invention. That is, the present invention clearly includes every type of transformation and modification that a person skilled in the art can realize according to the entire disclosure including the claims and to technological concept(s) thereof. In particular, with respect to the numerical ranges described in the present application, any numerical values or small ranges included in the ranges should be interpreted as being specifically described even if not otherwise explicitly recited.
SIGNS LIST
• 10 Camera
• 11 First camera
• 12A,12B Second cameras
• 20,20A,20B Moving body tracking system
• 21 Moving direction determining part
• 22 Path specifying part
• 23 Tracking target selecting part
• 24 Speed estimating part
• 25 Selection accepting and responding part
• 30 Network
• 40 Image tagging engine
• 50 Tagged captured data storage part
• 60 Moving body path data storage part
• 9000 Computer
• 9010 CPU
• 9020 Communication Interface
• 9030 Memory
• 9040 Auxiliary Storage Device
• V Vehicle

Claims (15)

What is claimed is:

1. A moving body tracking system, comprising:

a first camera that captures image(s) of moving body entering an intersection,

a plurality of second cameras installed in a plurality of locations set as destinations of the moving body entering the intersection,

a memory configured to store instructions, and

a processor configured to execute the instructions,

the instructions comprising:

determining a moving direction of the moving body entering the intersection due to a change in direction of the moving body based on captured data by the first camera, and

selecting the second camera based on the moving direction of the moving body, searches a frame in which the specified moving body was captured from captured data by the second camera, and specifies a path of the moving body.

2. The moving body tracking system according toclaim 1, further comprising estimating a speed of the moving body based on a location of the moving body recorded in the captured data by the first camera, and

selecting the captured data by the second camera based on the speed of the moving body.

3. The moving body tracking system according toclaim 1, wherein the cameras are installed in an intersection of an area in which an Origin-Destination (OD) survey is conducted, and the system comprises performing the OD survey by causing the cameras to function as the first and/or second camera(s).

4. The moving body tracking system according toclaim 1, wherein the first camera is installed at a position that allows to capture the moving body entering the intersection, from the front, back, left and right directions, and identify the moving direction of the moving body entering the intersection, from respective direction.

5. The moving body tracking system according toclaim 1, further comprising:

storing path information indicating a path for respective identified moving body, and

displaying map information displaying a path of the moving body accepted from a predetermined user terminal on a predetermined map.

6. A moving body tracking method, comprising:

determining a moving direction of a moving body entering an intersection based on a captured data by a first camera capturing the moving body entering the intersection, and

selecting a second camera from a plurality of cameras installed in a plurality of locations determined as destinations of the moving body entering the intersection based on the moving direction of the moving body, and specifying a moving path of the moving body by searching frame(s) in which the moving body is captured from the captured data of the second cameras.

7. The moving body tracking method according toclaim 6, further comprising:

estimating a speed of the moving body based on a location of the moving body recorded in the captured data by the camera, and

selecting the captured data by the second camera based on the speed of the moving body.

8. A computer-readable, non-transient recording medium storing a program for causing a computer that is capable of accessing captured data captured respectively, by

a first camera that captures an image(s) of a moving body entering an intersection, and

a plurality of second cameras installed in a plurality of locations determined as destinations of the moving body entering the intersection,

to perform:

a process that determines a path direction of the moving body entering the intersection based on the captured data by the first camera, and

a process that selects the second camera based on a path direction of the moving body, and specifies a path of the moving body by searching a frame(s) in which the moving body is captured from the captured data of the second camera.

9. The moving body tracking method according toclaim 6, wherein the cameras are installed in an intersection of an area in which an Origin-Destination (OD) survey is conducted, and the method comprises performing the OD survey by causing the cameras to function as the first and/or second camera(s).

10. The moving body tracking method according toclaim 6, wherein the first camera is installed at a position that allows to capture the moving body entering the intersection, from the front, back, left and right directions, and identify the moving direction of the moving body entering the intersection, from respective direction.

11. The moving body tracking method according toclaim 6 further comprising:

storing path information indicating a path for respective identified moving body, and

displaying map information displaying a path of the moving body accepted from a predetermined user terminal on a predetermined map.

12. The medium according toclaim 8, the program further comprising:

estimating a speed of the moving body based on a location of the moving body recorded in the captured data by the first camera, and

selecting the captured data by the second camera based on the speed of the moving body.

13. The medium according toclaim 8, wherein the cameras are installed in an intersection of an area in which an Origin-Destination (OD) survey is conducted, and the program comprises performing the OD survey by causing the cameras to function as the first and/or second camera(s).

14. The medium according toclaim 8, wherein the first camera is installed at a position that allows to capture the moving body entering the intersection, from the front, back, left and right directions, and identify the moving direction of the moving body entering the intersection, from respective direction.

15. The medium according toclaim 8, the program further comprising:

storing path information indicating a path for respective identified moving body, and

displaying map information displaying a path of the moving body accepted from a predetermined user terminal on a predetermined map.

Images